Benchmark

Siren AgentDojo Attack Success Rate Benchmark

What is Siren AgentDojo Attack Success Rate?

Siren AgentDojo evaluates tool-using agents under adversarial prompt-injection attacks. This metric is the attack success rate; lower is better.

Modality
text
Evaluates
safety, agents, tool calling
Openness
unknown
Importer
LLM Stats
Reported scores
1

Source provenance

Siren AgentDojo Attack Success Rate results and reported scores

LLM Stats

ModelOrganizationReported valueReportedEvidence
Muse Glimmer-30BMeta0.2842026-08-10evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.

Which sources cite Siren AgentDojo Attack Success Rate?

Related safety, agents, tool calling benchmarks